-Pattern Recognition and Biomedical signal processing:
- Heart Rate Variability (HRV)
- Wearable Medical Sensors
- Biomedical Signals Processing
- Pattern recognition
- Sleep Quality
- Circadian Cycles
- Health Technology Assessment (HTA)
-Machine learning techniques
- Naive Bayes Classifier
- Linear Discriminant Analysis
- Support Vector Machine
Research Associate in Biomedical Engineering at the University of Warwick, UK
Institute of Advanced Studies (IAS) Fellow at the University of Warwick, UK
Member of Applied Biomedical Signal Processing and Intelligent eHealth Lab at University of Warwick, Coventry, UK
Member of the Women in Medical and Biological engineering Committee of the International Federation Medical and Biological Engineering
Reviewer, Biomedical Signal Processing and Control Journal
Track Co-Chair, Women in Medical Physics and Biomedical Engineering Track, World Congress on Medical Physics and Biomedical Engineering 3-8th June, Prague, Czech Republic, 2018
Born in Naples, Italy, Rossana received her Ph.D and MSc degree in biomedical engineering at University of
Warwick. She is currently Research Associate at University of Warwick, where she has been an associate of the Applied Biomedical Signal Processing and Intelligent eHealth Lab since 2013. Her main areas of expertise are biomedical signal processing, machine learning and data analytics. She has authored or co-authored about 18 journal, book and conference papers. Rossana is member of the Italian Scientific society on Medical and Biomedical Engineering and member of the International Women Committee of the International Federation of Medical and Biomedical Engineering (IFMBE).
Research projects :
Circadian Rhythms, the Efficacy and Side Effects of Chemotherapy
Due to circadian rhythms, the efficacy and side effects of chemotherapy change throughout the day. Chemotherapy, in turn, alters circadian rhythm. This creates a closed-loop requiring control. While circadian rhythms can be monitored using blood/salivary/urine hormone tests, such tests are not practical at home and do not provide continuous real-time monitoring. Therefore, the main aim is to combine artificial intelligence (machine learning and deep learning) and signal processing with commercial sensors embedded in smartwatches or clothes that measure physiological and behavioural attributes (features/variables) to offer unprecedented and as yet unexplored opportunities to monitor circadian rhythms in real time.
Health Technology Assessment (HTA) of Medical Devices (MDs) in low and middle-income countries (LMIC)
The project is focused on Health Technology Assessment (HTA) of Medical Devices (MDs) in low and middle-income countries (LMIC), supporting the development of guidelines on HTA for LMICs.
In fact, the majority of medical devices are designed for Europe and USA, where there are clear standards and harmonized regulations on minimum requirements for design and maintenance of medical-location plants (i.e., electric, air and water plants in surgical theatres, ambulatory etc.). These standards and regulations allow transferring medical devices among hospitals/countries maintaining the same level of safety and efficacy. In many LMICs, those minimum requirements are not homogeneously guaranteed (and will not in the short term) and there is little evidence on how this affects patient safety, medical device efficacy and therefore the HTA of MDs. In order to measure the effects in safety and efficacy when MDs are operationalised in LMICs, and how this impacts on their HTA, field analyses are performed in sub-Saharan Africa (e.g., Burkina Faso, Benin, Mozambique or Nigeria). Plants and MDs in surgical theatres in sub-Saharan Africa are being analysed to quantify how far they are from meeting EU/USA standard and how this may affect medical device safety, efficacy and assessment.
Biomedical Signal Processing and Modelling for adverse Events prediction
Shifting healthcare monitoring techniques from the laboratory into real-life scenarios is very challenging. The current shift towards the use of advanced sensors into everyday objects (e.g., smart watch) is strongly increasing the need of reliable methods and tools to analyse healthcare information acquired into real-life settings for wellbeing applications.
Some of the main challenges and limitations arising from the application of traditional methods of signal processing, mainly developed to be used in laboratory settings were identified, and I proposed novel solutions to allow real-life monitoring of vital signs. In other words, my Ph.D. in biomedical engineering has been devoted to the translation of advanced methodologies and techniques from laboratory into real-life settings for prediction of adverse healthcare events.
My PhD activities resulted in 5 peer-reviewed published papers in first quartile journals. Moreover, 13 full-conference-papers were presented at international conferences. The research I have conducted over the years is highly interdisciplinary, combining engineering with knowledge from several medical specializations, computer science and business.
- 2018, IET William James Award, October 2018
- 2018, IAS Fellowship, Univerisity of Warwick
- 2017, Young Investigator Award 2017-Merit-June 2017, joined European Conference on Medical and Biological Engineering and North Baltic Conference 2017 (IFMBE EMBEC'17 & NBC'17), 11-15 June 2017, Tampere Finland
- 2017, ABTA Doctoral Researcher Awards- Honourable Mention- May 2017
- 2016, The runner-up prize in the Poster Competition School of Engineering Postgraduate Symposium- April 2016
- 2015, Young Investigator Award 2015-Merit- June 2015 – World Biomedical Engineering and Medical Physics 2015, June 7-12, 2015, Toronto, Canada.
(the updated list of publications can be seen on Google Scholar link)
Castaldo, R., Cavaliere, C., Soricelli, A., Salvatore, M., Pecchia, L., & Franzese, M. (2021). Radiomic and Genomic Machine Learning Method Performance for Prostate Cancer Diagnosis: Systematic Literature Review. Journal of medical Internet research, 23(4), e22394.
Castaldo, R., Chappell, M.J., Byrne, H., Innominato, P.F., Hughes, S., Pescapè, A. & Pecchia, L. (2021). Detection of melatonin-onset in real settings via wearable sensors and artificial intelligence. A pilot study. Biomedical Signal Processing and Control, 65, p.102386.
Stokes, K., Castaldo, R., Federici, C., Pagliara, S., Maccaro, A., Cappuccio, F., ... & Pecchia, L. (2022). The use of artificial intelligence systems in diagnosis of pneumonia via signs and symptoms: A systematic review. Biomedical Signal Processing and Control, 72, 103325.
Piaggio, D., Castaldo, R., Cinelli, M., Cinelli, S., Maccaro, A., & Pecchia, L. (2021). A framework for designing medical devices resilient to low-resource settings. Globalization and Health, 17(1), 1-13.
Stokes, K., Castaldo, R., Franzese, M., Salvatore, M., Fico, G., Pokvic, L. G., & Pecchia, L. (2021). A machine learning model for supporting symptom-based referral and diagnosis of bronchitis and pneumonia in limited resource settings. Biocybernetics and Biomedical Engineering, 41(4), 1288-1302.
- Castaldo R, Melillo P, Izzo R, De Luca N, Pecchia L, "Fall prediction in hypertensive patients via short-term HRV Analysis", IEEE Journal of Biomedical and Health Informatics, 2016 Mar 18, [Epub ahead of print], DOI: 10.1109/JBHI.2016.254396
- Castaldo, R., et al. "Acute mental stress assessment via short term HRV analysis in healthy adults: A systematic review with meta-analysis."Biomedical Signal Processing and Control 18 (2015): 370-377. Link
- Castaldo, R., P. Melillo, and L. Pecchia. "Acute Mental Stress Detection via Ultra-short term HRV Analysis." World Congress on Medical Physics and Biomedical Engineering, June 7-12, 2015, Toronto, Canada. Springer International Publishing, 2015. Link
- Castaldo R., Melillo P., and L. Pecchia. "Acute Mental Stress Assessment via Short Term HRV Analysis in Healthy Adults: A Systematic Review." 6th European Conference of the International Federation for Medical and Biological Engineering. Springer International Publishing, 2015. Link